deer-flow (bytedance/deer-flow) is an MCP server listed on the M8ven Trust Index. It scores 45 out of 100, grade D. It declares 60 tools. No publisher has claimed this listing.

Warning

45/100

deer-flow

Item: deer-flow
Rating: 45
Author: M8ven

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

→ bytedance/deer-flow · listed on github_code

Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

bytedance

Source: github_code

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

GitHub

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings

🚨

Reads files from sensitive locations

Touches: ~/.claude/.credentials.json

🔐

You'll be asked for 9 credentials: GITHUB_OAUTH_TOKEN, OPENAI_API_KEY, PROVISIONER_API_KEY, BRAVE_SEARCH_API_KEY, BROWSERLESS_TOKEN, CRW_API_KEY, GROUNDROUTE_API_KEY, SERPER_API_KEY, SERPLY_API_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

configDEERFLOW_RECORD_OUT

configE2E_AUTH_FRONTEND_PORT

configE2E_FRONTEND_PORT

configE2E_GATEWAY_PORT

🔐 secretGITHUB_OAUTH_TOKEN

configOPENAI_API_BASE

🔐 secretOPENAI_API_KEY

configPLAYWRIGHT_AUTH_BASE_URL

configPLAYWRIGHT_BASE_URL

configPLAYWRIGHT_SKIP_WEB_SERVER

configRECORD_MODEL

configK8S_NAMESPACE

configLARK_CLI_INIT_IMAGEon the provisioner; it stays off (legacy behavior) when

configLARK_CLI_BROKER_IMAGE

configDEERFLOW_LARK_BROKER_DENY_SUBCOMMANDS

configTHREADS_HOST_PATH

configDEER_FLOW_HOST_BASE_DIR

configSKILLS_PVC_NAME

configSKILLS_PVC_SUBPATH_TEMPLATE

configSANDBOX_CONTAINER_PORT

configSANDBOX_SERVICE_TYPE

configKUBECONFIG_PATH

🔐 secretPROVISIONER_API_KEY

configK8S_API_SERVER

🔐 secretBRAVE_SEARCH_API_KEY

🔐 secretBROWSERLESS_TOKEN

🔐 secretCRW_API_KEY

configCRW_API_URL

🔐 secretGROUNDROUTE_API_KEY

🔐 secretSERPER_API_KEY

🔐 secretSERPLY_API_KEY

configDEER_FLOW_CONFIG_PATH

configDEER_FLOW_STREAM_BRIDGE_REDIS_URL

configDEER_FLOW_SANDBOX_OWNERSHIP_REDIS_URL

configUV_EXTRAS

configCODEX_AUTH_PATH

configCLAUDE_CODE_CREDENTIALS_PATHClaude Code accepts CLAUDE_CODE_OAUTH_TOKEN, ANTHROPIC_AUTH_TOKEN, , or ~/.claude/.credentials.json

configCLAUDE_CODE_CUSTOM_OAUTH_URL

configUSE_LOCAL_OAUTH

configLOCAL_BRIDGE

configUSE_STAGING_OAUTH

configCLAUDE_CONFIG_DIR

configRECORD_PORT

configDEER_FLOW_HOME

configDEER_FLOW_EXTENSIONS_CONFIG_PATH

configPYTHONPATH

configDEERFLOW_REPLAY_FIXTURE

configGATEWAY_CORS_ORIGINS

configDEERFLOW_ENABLE_TEST_SEED

configGATEWAY_WORKERS

Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.

deployNEXT_PUBLIC_APP_VERSION

deployNEXT_PUBLIC_BACKEND_BASE_URL

deployNEXT_PUBLIC_LANGGRAPH_BASE_URL

deployNEXT_PUBLIC_STATIC_WEBSITE_ONLY

// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

60/60 tools missing one or more hints — bash_tool (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ls_tool (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); glob_tool (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +57 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

37/60 tools referenced in tests (62%)

Write tests that reference each tool by name so every tool has at least one test.

No access to sensitive paths

Reads sensitive paths: ~/.claude/.credentials.json

Remove reads of sensitive system paths. If you genuinely need them, document why in the README.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Verified](https://m8ven.ai/badge/mcp/bytedance/deer-flow?variant=verified)](https://m8ven.ai/mcp/bytedance/deer-flow)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: 83cb6767b3624669b98509dc3670280c95f49f4e

code hash: 9122ba45c4939d0432a0bda7f90df5cc10c1017562245eba65269c240130d30d

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client